See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-Math-7B-Instruct
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 75ce22dd8f71e872_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/75ce22dd8f71e872_train_data.json
  type:
    field_input: linked_columns
    field_instruction: template
    field_output: ref
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56a3/ac1cf790-5dbe-4fd8-9daa-76f1ec77f7ab
hub_strategy: checkpoint
hub_token: null
hub_username: dada22231
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
  1: 70GiB
  2: 70GiB
  3: 70GiB
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/75ce22dd8f71e872_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: ac1cf790-5dbe-4fd8-9daa-76f1ec77f7ab
wandb_project: god
wandb_run: xf1i
wandb_runid: ac1cf790-5dbe-4fd8-9daa-76f1ec77f7ab
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

ac1cf790-5dbe-4fd8-9daa-76f1ec77f7ab

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8604

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 8
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
5.252	0.0035	1	6.0495
3.1826	0.0868	25	2.7080
2.8019	0.1736	50	2.2575
2.1921	0.2604	75	2.0858
2.29	0.3472	100	1.9780
2.1169	0.4340	125	1.9305
2.0913	0.5208	150	1.8919
1.9978	0.6076	175	1.8730
1.9518	0.6944	200	1.8604

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1